Papers › Label-Only Model Inversion Attacks via Knowledge Transfer

Label-Only Model Inversion Attacks via Knowledge Transfer

30 Oct 2023NeurIPS 2023 11arXiv:2310.19342archive 2025-07-28

In a model inversion (MI) attack, an adversary abuses access to a machine learning (ML) model to infer and reconstruct private training data. Remarkable progress has been made in the white-box and black-box setups, where the adversary has access to the complete model or the model's soft output respectively. However, there is very limited study in the most challenging but practically important setup: Label-only MI attacks, where the adversary only has access to the model's predicted label (hard label) without confidence scores nor any other model information. In this work, we propose LOKT, a novel approach for label-only MI attacks. Our idea is based on transfer of knowledge from the opaque target model to surrogate models. Subsequently, using these surrogate models, our approach can harness advanced white-box attacks. We propose knowledge transfer based on generative modelling, and introduce a new model, Target model-assisted ACGAN (T-ACGAN), for effective knowledge transfer. Our method casts the challenging label-only MI into the more tractable white-box setup. We provide analysis to support that surrogate models based on our approach serve as effective proxies for the target model for MI. Our experiments show that our method significantly outperforms existing SOTA Label-only MI attack by more than 15% across all MI benchmarks. Furthermore, our method compares favorably in terms of query budget. Our study highlights rising privacy threats for ML models even when minimal information (i.e., hard labels) is exposed. Our study highlights rising privacy threats for ML models even when minimal information (i.e., hard labels) is exposed. Our code, demo, models and reconstructed data are available at our project page: https://ngoc-nguyen-0.github.io/lokt/

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 31 code samples: 30 from 4 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 31: 15 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 16 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 4 ran (1 with no instrument failure; 3 where Syntology's instrument failed); found in paper text by Syntology: 19 samples from 2 repositories, 9 ran (7 with no instrument failure; 2 where Syntology's instrument failed); community: 4 samples from 1 repository, 2 ran (1 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 15 samples that ran have no recorded date.

ngoc-nguyen-0/LOKT_neurips2023 officialpytorchSyntology: 7 samples, 4 ran (3 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 15 ran (of which 1 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 0 violated, 6 with no contract checked; 6 where Syntology's instrument failed) · 16 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
5ran · our draft was wrong
1ran; the contract check could not run
6ran
16unverified

Licence: 17 of the 31 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 4 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample is listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ngoc-nguyen-0/LOKT_neurips2023 official repository 7 samples, 4 ran (3 instrument-failed) · 3 unverified
cross_entropy_loss in 58 papers plg_tacgan.py ran · our draft was wrong no licence file found · pointer only · c808ba0601a877e8 · report fixture: signature out:Tensor/2/float, iden:Tensor/1/int · returned Tensor · level recorded 2026-09-24
max_margin_loss plg_tacgan.py ran · our draft was wrong no licence file found · pointer only · 342f31bfe572d0c8 · report fixture: signature out:Tensor/2/float, iden:Tensor/1/int · returned Tensor · level recorded 2026-09-22
poincare_loss in 6 papers plg_tacgan.py ran · our draft was wrong no licence file found · pointer only · b6e4cb9cdcdb7226 · report fixture: signature outputs:Tensor/2/float, targets:Tensor/1/int, xi:float/0/float · returned Tensor · level recorded 2026-09-22
sample_z in 5 papers plg_tacgan.py ran · honoured contract no licence file found · pointer only · e419b5eab5a4c10e · report fixture: signature batch_size:int/0/int, dim_z:int/0/int, device:device/0/?, distribution:str/0/str · returned Tensor · level recorded 2026-09-22
inversion plg_tacgan.py unverified no licence file found · pointer only · 32b21a45b3401a1a · report
save_tensor_images plg_tacgan.py unverified no licence file found · pointer only · 8a7eec0e2a16469a · report
set_random_seed in 12 papers plg_tacgan.py unverified no licence file found · pointer only · e4778d33af343c8c · report
AlanPeng0897/Defend_MI found in paper text by Syntology 18 samples, 8 ran (2 instrument-failed) · 10 unverified
ResNet18 in 174 papers BiDO/model.py ran MIT (permissive) · 4d7100d163a0ad4f · report fixture: signature n_classes:int/0/int, hsic_training:bool/0/bool · returned ResNet · level recorded 2026-09-24
get_in_channels BiDO/model.py ran MIT (permissive) · 5140f76be90b05a2 · report fixture: signature data_code:str/0/str · returned int · level recorded 2026-09-24
gram_schmidt in 32 papers VMI/layers.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · c41836f3e51fa8f1 · report fixture: signature x:Tensor/2/float, ys:list/1/Tensor · returned Tensor · level recorded 2026-09-22
imread in 54 papers GMI/fid_score_raw.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · aa4cae054b657ba2 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-22
imread in 54 papers DMI/fid_score.py ran MIT (permissive) · e8dfc0e2df364d99 · report fixture: signature dataset:str/0/str, filename:str/0/str · returned ndarray · level recorded 2026-09-24
imread in 54 papers DMI/fid_score_raw.py ran MIT (permissive) · 7a46ab6d33c637db · report fixture: signature dataset:str/0/str, filename:str/0/str · returned ndarray · level recorded 2026-09-24
make_layers in 155 papers BiDO/model.py ran MIT (permissive) · d8ff7dc2584b42c8 · report fixture: signature cfg:list/1/int, batch_norm:bool/0/bool · returned list · level recorded 2026-09-25
power_iteration in 30 papers VMI/layers.py ran · our draft was wrong MIT (permissive) · 28d3a35157f2916d · report fixture: signature W:Tensor/2/float, u_:list/1/Tensor, update:bool/0/bool, eps:float/0/float · returned tuple · level recorded 2026-09-25
ResNet10 in 15 papers BiDO/backbone.py unverified MIT (permissive) · d30f849071ebea54 · report
ResNet10_64 BiDO/backbone.py unverified MIT (permissive) · 83d772c48bd4e1cc · report
ResNetL_IH BiDO/backbone.py unverified MIT (permissive) · 231adc85ec00eba1 · report
calculate_frechet_distance in 119 papers DMI/fid_score.py unverified MIT (permissive) · 0def50a351111624 · report
get_activations in 100 papers GMI/fid_score_raw.py unverified MIT (permissive) here; the stored copy is pointer only · 56afde1af5757691 · report
get_activations in 100 papers DMI/fid_score.py unverified MIT (permissive) · 8dcbb65408aae9e3 · report
get_activations in 100 papers DMI/fid_score_raw.py unverified MIT (permissive) · c945372835eb9223 · report
get_activations in 100 papers GMI/fid_score.py unverified MIT (permissive) · 7a33df383fc5fb9d · report
parse_kwargs VMI/model_utils.py unverified MIT (permissive) · cd1a232569d08a1b · report
proj in 38 papers VMI/layers.py unverified MIT (permissive) here; the stored copy is pointer only · 4015ab1f3ab9b881 · report
Jiachen-T-Wang/mi-defense found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Inversion knowledge_align/model.py ran no licence file found · pointer only · 91738ef0d0844a36 · report fixture: returned Inversion · level recorded 2026-09-22
val-iisc/hard-label-model-stealing community 4 samples, 2 ran (1 instrument-failed) · 2 unverified
filter_indices code/train_student/train_student.py ran · honoured contract no licence file found · pointer only · 6d7145cc1578db8c · report fixture: signature trainset:SimpleDataset/0/?, classes_indices:list/1/int · returned list · level recorded, date not recorded
mixup_data in 51 papers code/train_student/train_student.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9917ee672087e236 · report fixture: returned tuple · level recorded, date not recorded
filter_indices code/train_generator/train_gen.py unverified no licence file found · pointer only · c9de4689c018d059 · report
get_model_accuracy code/train_generator/train_gen.py unverified no licence file found · pointer only · 9dcd16e6960e3b6b · report
Repository not located 1 sample, 0 ran · 1 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
rand_bbox in 63 papers repository not located unverified licence of this copy not recorded · d34a085d71b8f4b5 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for LOKT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for LOKT (graph method: LOKT). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. Inversion entry · level 1 · ran · 91738ef0d0844a36

harvested Assembly for LOKT (graph method: LOKT). 7 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. inversion entry · level 0 · unverified · 32b21a45b3401a1a
  2. cross_entropy_loss loss · level 1 · ran · our draft was wrong · c808ba0601a877e8
  3. max_margin_loss loss · level 1 · ran · our draft was wrong · 342f31bfe572d0c8
  4. poincare_loss loss · level 1 · ran · our draft was wrong · b6e4cb9cdcdb7226
  5. sample_z helper · level 1 · ran · honoured contract · e419b5eab5a4c10e
  6. save_tensor_images helper · level 0 · unverified · 8a7eec0e2a16469a
  7. set_random_seed helper · level 0 · unverified · e4778d33af343c8c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2310.19342") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Transfer Learningmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections